Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2344 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0509. Min Range: -1.0509

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1432600 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1197545 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8884. Min Act: -0.0000

Data Index: 596845 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1363910 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1628437 (Python Code)

Max Activating Token Index: 990

Text #5

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7674. Min Act: -0.0000

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1333326 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1526269 (Python Code)

Max Activating Token Index: 329

Text #8

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7426. Min Act: -0.0000

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1192776 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1440356 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1379587 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1059305 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1385348 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1426007 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1384772 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1128152 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6550. Min Act: -0.0000

Data Index: 624807 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1309354 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.0509. Min Range: -1.0509

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1584330 (Python Code)

Max Activating Token Index: 253